19 of 561 catalog entries

Official — built on Jev

First-party Jev resources published by TypeSafe AI: the company site, documentation, quick start, HTTP API reference, and community Discord. Everything listed here is maintained upstream, not by this directory.

Use these links to verify the numbers quoted across this site — such as list pricing of $0.042 per 1M input tokens with output tokens free, and an end-to-end latency range of roughly 70–500ms. Those figures come from TypeSafe materials, not from benchmarks run here.

GitHub451

TypeSafe agent skills

Official agent skill for Claude Code, Codex, and compatible agents: primitives, patterns, and how to structure evaluations.

github.comOpen
GitHub306

System One adapter (Python)

Official drop-in TypeSafeClient replacement backed by OpenAI, Anthropic, and compatible LLM APIs, for comparing Jev against chat models.

github.comOpen
Project page245

TypeSafe JavaScript SDK

Official TypeScript/JavaScript client with inferred answer types. npm install @typesafe-ai/sdk.

On-site pageView
Project page231

TypeSafe Python SDK

Official sync and async Python client. pip install typesafe-sdk.

On-site pageView
External

@typesafeai on X

Product and research updates.

x.comOpen
External

Cookbooks

Reproducible recipes: parallel questions, reranking, guardrails, citation checks, extraction, hierarchical classification.

docs.typesafe.aiOpen
External

Discord

Official TypeSafe server. Builder demos live in the Show and Tell channel.

discord.ggOpen
External

Documentation

Introduction, primitives, patterns, cookbooks, HTTP API, and SDK references.

docs.typesafe.aiOpen
External

HTTP API reference

Request and response contract for POST /v1/systemone.

docs.typesafe.aiOpen
External

Introducing System One Models and Jev

Launch post: architecture, RLCD training, pricing, Doom and Wikiracing demos, FAQ.

typesafe.aiOpen
External

Jev 1.13 jaggedness

Known failure modes of the current public model, documented by TypeSafe.

docs.typesafe.aiOpen
External

Manifesto

The case for machine-native intelligence built for software, not conversation.

typesafe.aiOpen
External

Patterns

Speculative fan-out, confidence-gated routing, composite scoring, and intent routing.

docs.typesafe.aiOpen
External

Playground

Paste a state, add questions, and see typed answers in the browser.

console.typesafe.aiOpen
External

Primitives

Choice, Score, and Noul: the three question types and what they return.

docs.typesafe.aiOpen
External

Quick start

Shortest path from an API key to a typed decision.

docs.typesafe.aiOpen
External

Smart home demo

Official interactive demo of speculative fan-out: many questions in one call, code keeps the relevant answers.

docs.typesafe.aiOpen
External

TypeSafe AI

Company homepage, waitlist, and product overview.

typesafe.aiOpen
External

Workflow evals

Published eval methodology and per-model results for System One workflows.

evals.typesafe.aiOpen

Jev patterns that pair with official Jev resources

Browse other categories